Deep learning has presented remarkable progress in various tasks. Despite the excellent
performance, deep learning models remain not robust, especially to well-designed …

The design and control of autonomous systems that operate in uncertain or adversarial
environments can be facilitated by formal modeling and analysis. Probabilistic model …

This paper concerns the efficient construction of a safety shield for reinforcement learning.
We specifically target scenarios that incorporate uncertainty and use Markov decision …

Safe exploration is a common problem in reinforcement learning (RL) that aims to prevent
agents from making disastrous decisions while exploring their environment. A family of …

We study safe policy improvement (SPI) for partially observable Markov decision processes
(POMDPs). SPI is an offline reinforcement learning (RL) problem that assumes access to (1) …

This position paper reflects on the state-of-the-art in decision-making under uncertainty. A
classical assumption is that probabilities can sufficiently capture all uncertainty in a system …

The rapid advance of deep reinforcement learning techniques enables the oversight of
safety-critical systems through the utilization of Deep Neural Networks (DNNs). This …

This paper marries two state-of-the-art controller synthesis methods for partially observable
Markov decision processes (POMDPs), a prominent model in sequential decision making …

Deep reinforcement learning has been successfully applied to many control tasks, but the
application of such controllers in safety-critical scenarios has been limited due to safety …

We consider the problem: is the optimal expected total reward to reach a goal state in a
partially observable Markov decision process (POMDP) below a given threshold? We tackle …